© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7355
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    社ä¼ļèµĦæľ¬
    -0.31
    onden
    -0.26
    reich
    -0.26
    ona
    -0.26
     Train
    -0.26
    å¦ĤæĦı
    -0.26
    翦
    -0.24
    éĦ¯
    -0.24
     nós
    -0.23
    ç¾Ķ
    -0.23
    POSITIVE LOGITS
    abeth
    0.30
    istik
    0.27
    æķı
    0.25
    wall
    0.24
    ')");↵
    0.24
    åºĶæĢ¥ç®¡çIJĨ
    0.23
    æľīæĿĥ
    0.23
    ****/↵
    0.23
    ').'
    0.23
    @brief
    0.23
    Activations Density 0.805%

    No Known Activations

    This feature has no known activations.